EP0796463B1 - Mechanismus für eine konfigurierung - Google Patents

Mechanismus für eine konfigurierung Download PDF

Info

Publication number
EP0796463B1
EP0796463B1 EP95941311A EP95941311A EP0796463B1 EP 0796463 B1 EP0796463 B1 EP 0796463B1 EP 95941311 A EP95941311 A EP 95941311A EP 95941311 A EP95941311 A EP 95941311A EP 0796463 B1 EP0796463 B1 EP 0796463B1
Authority
EP
European Patent Office
Prior art keywords
processor
processors
distribution
redundancy
distribution units
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
EP95941311A
Other languages
English (en)
French (fr)
Other versions
EP0796463A2 (de
Inventor
Anna Naemi Ingeborg Holte-Rost
Sofia Birgitta Andersson
Ramon Alexander Larruy
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Telefonaktiebolaget LM Ericsson AB
Original Assignee
Telefonaktiebolaget LM Ericsson AB
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Telefonaktiebolaget LM Ericsson AB filed Critical Telefonaktiebolaget LM Ericsson AB
Publication of EP0796463A2 publication Critical patent/EP0796463A2/de
Application granted granted Critical
Publication of EP0796463B1 publication Critical patent/EP0796463B1/de
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5083—Techniques for rebalancing the load in a distributed system
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2209/00—Indexing scheme relating to G06F9/00
    • G06F2209/50—Indexing scheme relating to G06F9/50
    • G06F2209/5019—Workload prediction

Definitions

  • a Distribution Unit may encompass a number of resources, and what the Distribution Unit actually comprises is dependent on the application in question. Thus it can be almost anything from groups of objects in data bases to process allocated objects representing hardware.
  • a very common object making up a Distribution Unit is a group of data representing individual subscribers connected to the telecommunications system.
  • Each Distribution Unit has a unique identity, that can be used by an application subfunction addressing the Distribution Unit. This identity is composed of one part identifying the application subfunction with which the Distribution Unit in question is associated, and one part identifying the Distribution Unit within this application subfunction.
  • the common identifier for objects of an Distribution Unit may be the last two digits of a telephone number, which would create 100 Distribution Units.
  • each Distribution Unit can be independently allocated to a processor.
  • the number of Distribution Units defined by an application determines the maximum number of processors that this application might be distributed to.
  • Another advantage is an improved addressing capacity, because the length of lists in the addressing mechanisms are dramatically shortened.
  • the "address field" will also be shorter.
  • Redundancy Domain means a specified number of processors on which code for one and the same application subfunction is loaded, such that the subfunction in question may be executed on all processors in the Redundancy Domain. The number of processors within the Domain may be changed during runtime. The "redundancy” resides in the fact that the system will continue to function even if a processor is crashed or blocked.
  • Load means the relative utilization of each processor in the system at any given time.
  • Load imbalance means a deviation from a desired load that may trigger a reconfiguration. Thus, minor imbalances within predefined limits are tolerated.
  • “Application” means something executing on a distributed computer system, e.g. telecommunications system. Examples of “Applications” are telephone calling systems, ISDN.
  • Application Subfunction means elementary or basic processes together forming an "Application” (e.g. "off-hook” and “call access” functions, code receiving functions etc.).
  • the code of each subfunction may be executed on several processors. Each processor handles different D.U.'s.
  • the present invention relates in one aspect to methods for configuration and reconfiguration of software resources and of the execution of such resources, in a distributed computer system, in particular a telecommunications system.
  • the present invention relates to a telecommunications system having built in functionality for such configuration and reconfiguration.
  • Such mechanisms for "run time adjustments" of configurations are dependent on continuous supply of information of the status of the system, in terms of e.g the load balance in the system. This information can be acquired by monitoring the system with respect to certain parameters for a longer period of time. Data from such measurements would notify the change of load of the processors over the time, e.g. that some processors most of the time are more loaded than others. Such information may be used for initiating reconfigurations in the system, either by a maintenance technician or by functionality "built in” in the system. To enable such run time reconfigurations to be made, while fulfilling the requirements concerning non-disturbance of the operation of the system, there must be powerful mechanisms in the operating system supporting such reconfiguration, and applied by the applications.
  • US-5,165,018 discloses self-configuration of nodes in a distributed message-based operating system. Run-time configuration is achieved by node-based configuration management processes in accordance with information contained in resource definition messages.
  • D.U. Distribution Units
  • An advantage of the invention is the improved handling. It becomes simpler to configure the system since the distribution of the D.U.'s is supported by the operating system. Since the OS supports load balancing in runtime the requirement of perfect initial configuration becomes less demanding. The need for acute operator action is reduced. Also since the OS supports the Redundancy Relocation at processor loss, a service person does not need to instantly visit the location.
  • Still another advantage of the invention is the inherent robustness, i.e. the system will be able to automatically take care of load imbalances due to certain types of anomalities, e.g. processor crash etc.
  • the disturbance on the system is reduced, and the load distribution over remaining processors will be maintained.
  • the built-in Redundancy Relocation reduces the time that a function is unavailable due to e.g. processor loss.
  • the cost will be reduced by virtue of the built-in load balancing, since the processor utilization thereby will be advantageously improved. It may even be possible to reduce the number of processors in the system by more efficiently distributing Resources over processors.
  • the prerequiseted mechanisms are:
  • Scheme 1 for distribution of Distribution Units on the processors within the Redundancy Domain, describes how to distribute the Resources of the system, grouped as Distribution Units (as defined previously herein) over the processors in the system, taking into account parameters determining the capacity of each processor, optionally measured values of load.
  • This scheme will outpoint for each Distribution Unit indicating to which processor it will be relocated in the case of a reconfiguration at a later stage, e.g. in situations a - f above.
  • Fig. 1a there is shown a simplified overview of a telecommunications system. It comprises several subscribers, each having at least one telephone 1. Each telephone is connected to the system via a so called LIC (Line Interface Circuit), which in its turn is connected to a switch 2 responsible for the communication between all units in the system. On all processors 3 in the system there are one or more subfunctions executing. There is also provided a data base 4 containing subscriber data etc. The data base is part of the operating system executing on the processors, and normally resides in primary memory (some of the processors may also be equipped with a disk, that may contain the data base). The disks are otherwise primarily used as loading media and for back up purposes, but may also have other functions.
  • LIC Line Interface Circuit
  • Fig. 1b there is shown three processors 3 forming a Redundancy Domain (indicated in broken lines), as defined previously, in the system of Fig. 1a.
  • Each processor is loaded with code for an application subfunction APPL and an operating system OS, comprising the data base.
  • Fig. 1c there has been defined 30 Distribution Units with identifiers in a sequence from 0-29. In this example they are divided into three groups (equally distributed), because there are three equal processors within the defined Redundancy Domain.
  • the scheme is calculated in order to keep the suites of Distribution Units in a consecutive order to the greatest extent possible.
  • Fig. 2a shows a simple flow chart of an Initial Configuration.
  • the operating system In the first step, during input of data (normally data is written to a file which is then read by the O.S.), the operating system is provided with information about which application subfunction(s) the configuration is to handle; how the Redundancy Domain is defined; and the suite of Distribution Units that are to be distributed in the configuration. In response to said data, the operating system will calculate the Scheme of Distribution of DU's over the active processors in the Redundancy Domain (Fig. 1c).
  • the code for the application subfunction(s) will be loaded on the processors in the Redundancy Domain in question, and subsequently the DU's will be installed in accordance with the previously calculated Distribution Scheme, whereby the application Distribution Units are distributed over (and started on) the processors in the domain.
  • the simplest algorithm is to distribute the Distribution Units as equally as possible over the active processors within the Redundancy Domain.
  • the algorithm may also already initially consider the memory capacity of the processor, the execution capacity of the processor, and the capacity used by other applications executing on the processors.
  • the number of Distribution Units allocated to individual processors will be weighted in proportion to such considerations.
  • Figure 2b shows how the Distribution Units allocated to a processor, will be divided into suites, that in case of blocking of a processor will be moved to the most suitable processor still in operation.
  • the arrows in the figure indicates how DU's will be moved from a processor to another in case of processor loss.
  • the distribution algorithm preferably maintains the identities of Distribution Units allocated to a processor in sequence, such that when Distribution Units are relocated to another processor during reconfiguration, they will be relocated to maintain the identities of Distribution Units on each processor in sequence to the greatest extent possible (discussed and exemplified further below). In this way the addressing will be much more rapid, because providing sequences in the address tables yield fewer lines in the tables.
  • the distribution of the Distribution Units (0..29) amongst the processors has resulted in a suite of 10 Distribution Units per processor (0..9), (10..19), (20..29). Each one of the suites (0..9), ... will be divided into two equally large parts, that will be separately moved to the two remaining processors, in case of a processor blocking.
  • the scheme of automatic redundancy relocation will be recalculated after performance of a redundancy relocation, and after each kind of other reconfiguration affecting the distribution.
  • an interface For operation and maintenance of the application subfunction, an interface is required. Such an interface will have facilities for initial installation of Distribution Units (INSTALL), removal (REMOVE) of Distribution Units, and for moving Distribution Units from one application subfunction executing on one processor to another subfunction executing on another processor. Further functions are SHUTDOWN and TAKEOVER. Said functions are basically implemented as programs triggering certain activities, and are briefly described below.
  • SHUTDOWN prepares for termination and a forthcoming take over.
  • TAKEOVER transfers control of resource objects in an old static process to a new static process.
  • Reconfiguration may be made either manually by an operator or automatically by the system itself, such as when certain limit values in e.g. load are exceeded.
  • Manual reconfiguration is extremely complex, and therefore the methods disclosed herein are implemented in the operating system.
  • the activities that may be initiated by a maintenance technician in run time are the following:
  • Fig. 3a an example could be an increased number of subscribers in a telecommunications system. This will cause a new scheme of distribution (and redundancy relocation).
  • Fig. 3b there is shown an additional installation of the Distribution Units (30-39), applied to our example.
  • the system must be "informed” that 10 new Distribution Units (30-39) will be added.
  • data is written to a file which is read by the operating system.
  • the scheme of distribution of the Distribution Units amongst the processors within the domain will then be recalculated (0..12), (13..26), (27..29) by the operating system in response to input data.
  • the additional (new) Distribution Units are INSTALLED and the other (original) Distribution Units are moved to processors according to the new Scheme of Distribution (with "SHUTDOWN" towards the "old” processes, and “TAKEOVER” against the "new” processes.
  • the operating system detects a crash by mechanisms known per se. When a crash is detected immediately the DU's allocated to the lost processor will be INSTALLED in accordance with the Redundancy Relocation Scheme calculated at Initial Configuration, or with the last updated Scheme in the case that some event has triggered a recalculation for other reasons. In a more complex situation, additionally some DU's on the still active processors may have to be moved to meet e.g. the load balance criteria.
  • Fig. 6b shows an example of an automatic relocation of Distribution Units, caused by an automatic blocking of a processor (processor crash).
  • Distribution Units allocated to processor 2 are moved so as to be allocated to processor 1 (DU's 10..14) and processor 3 (DU's 15..19) with "INSTALL" against the "new" processes.
  • Fig. 7c The process of adding a new processor is shown in Fig. 7c.
  • the system In the first step the system must be informed similarly to the case of Initial Configuration, i.e. what application subfunctions are used, and what the Redundancy Domain is. Then the new processor is loaded with code for the application subfunctions in question, and finally the processor is blocked.
  • Fig 7a is a flowchart showing the sequence of steps occurring when a processor is taken into operation again after having been blocked.
  • the operating system detects that a processor has been added or has been reinstalled (both cases are identical from the operating systems point of view. The way detection is carried out is irrelevant, and could be effected by an operator action or by software checking the available slots whether a processor is present or not. The skilled man will appreciate that there are many ways of achieving this function.
  • the operating system calculates a new Scheme of Distribution including the deblocked processor.
  • Fig. 7b shows how the Distribution Units (10..14) and (15..19), are moved between the involved processors (with “shutdown” towards the “old” process and “takeover” against the “new” processes) in order to attain the new scheme of distribution.

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Hardware Redundancy (AREA)
  • Multi Processors (AREA)
  • Steering Control In Accordance With Driving Conditions (AREA)
  • Surgical Instruments (AREA)
  • Lock And Its Accessories (AREA)
  • Water Treatment By Sorption (AREA)
  • Pharmaceuticals Containing Other Organic And Inorganic Compounds (AREA)
  • Switches With Compound Operations (AREA)
  • Paper (AREA)
  • Undergarments, Swaddling Clothes, Handkerchiefs Or Underwear Materials (AREA)
  • Computer And Data Communications (AREA)
  • Telephonic Communication Services (AREA)
  • Exchange Systems With Centralized Control (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Claims (16)

  1. Verfahren für eine Konfiguration eines verteilten Computersystems,
    gekennzeichnet durch
    die folgenden Schritte:
    a) Gruppieren von Softwareressourcen in Verteilungseinheiten;
    b) Laden eines Codes für eine Anwendungs-Subfunktion auf mehreren oder sämtlichen Prozessoren in dem System, wobei die Prozessoren, auf denen eine Subfunktion ausgeführt wird, dadurch eine Redundanzdomäne bilden;
    c) anfängliches Verteilen der Verteilungseinheiten über die Prozessoren in der Redundanzdomäne derart, dass die Prozessorlast in vernünftiger Weise ausgeglichen ist;
    d) Erzeugen eines Redundanzumordnungsschemas, indem jeder Verteilungseinheit auf einem Prozessor in der Redundanzdomäne ein jeweiliger anderer Prozessor innerhalb der Redundanzdomäne zugewiesen wird, wobei das Redundanzumordnungsschema eine Umordnung von einer oder mehreren der Verteilungseinheiten auf einem Prozessor an einen oder mehrere der anderen Prozessoren innerhalb der gleichen Redundanzdomäne erlaubt, sollte sich als Folge von Lastungleichgewichten oder anderen Fehlfunktionen des Systems eine Notwendigkeit ergeben.
  2. Verfahren nach Anspruch 1,
    gekennzeichnet durch
    ein anfängliches Bestimmen, wieviel Prozessorkapazität von jeder Anwendungs-Subfunktion, die auf dem System ausgeführt wird, benötigt wird; und ein Bestimmen der Anzahl von Prozessoren, auf denen jede Anwendungs-Subfunktion laufen muss, wobei die Anzahl von Prozessoren eine Redundanzdomäne bilden.
  3. Verfahren nach Anspruch 1,
    dadurch gekennzeichnet,
    dass die anfängliche Verteilung auf Grundlage von Parametern durchgeführt wird, die die Kapazität jedes Prozessors in dem System bestimmen.
  4. Verfahren nach Anspruch 3,
    dadurch gekennzeichnet,
    dass die anfängliche Verteilung die erwartete Last auf den Prozessoren in der Redundanzdomäne berücksichtigt, wobei die erwartete Last optional auf historischen Daten der Prozessorlast basiert.
  5. Verfahren nach Anspruch 2,
    gekennzeichnet durch
    ein Bilden von mehreren Redundanzdomänen innerhalb des Systems, wobei jede Redundanzdomäne eine jeweilige Anzahl von Prozessoren umfasst.
  6. Verfahren nach Anspruch 1 oder 5,
    gekennzeichnet durch
    ein aufeinanderfolgendes Nummerieren der Verteilungseinheiten und ein Umordnen der einen oder mehreren Verteilungseinheiten in einer derartigen Weise, dass die Verteilungseinheiten so weit wie möglich in einer Sequenz auf dem einen oder mehreren anderen Prozessoren geordnet sein werden.
  7. Verfahren nach Anspruch 1, ferner
    gekennzeichnet durch
    die folgenden Schritte:
    e) kontinuierliches Überwachen des Zustands jedes
    Prozessors während eines Betriebs, um Änderungen in der Last zu erfassen, was ein Lastungleichgewicht zwischen den Prozessoren verursacht;
    f) im Ansprechen auf ein erfasstes Ungleichgewicht, Berechnen eines neuen Verteilungsschemas für die Verteilungseinheiten über die Prozessoren, wobei die berechnete Verteilung proportional zu der Änderung des Lastgleichgewichts der Prozessoren gewichtet wird;
    g) Umordnen von Verteilungseinheiten von einem stark belasteten Prozessor an andere weniger belastete Prozessoren in Übereinstimmung mit der berechneten neuen Verteilung; und
    h) Transferieren einer Verarbeitung von dem stark belasteten Prozessor an den weniger stark belasteten Prozessor (die weniger stark belasteten Prozessoren).
  8. Verfahren nach Anspruch 7,
    dadurch gekennzeichnet,
    dass der Schritt zum Umordnen von Verteilungseinheiten ein Kopieren von Verteilungseinheiten von dem stark belasteten Prozessor an einen weniger belasteten beinhaltet, während die ursprünglichen Daten noch auf dem stark belasteten Prozessor in Betrieb sind.
  9. Verfahren nach Anspruch 8,
    dadurch gekennzeichnet,
    dass die Verteilungseinheiten aufeinanderfolgend nummeriert sind und ursprünglich in einer Sequenz auf jeden Prozessor verteilt sind, und wobei die berechnete neue Verteilung Verteilungseinheiten an andere Prozessoren derart umordnet, dass die Nummernsequenzen zu dem größtmöglichen Ausmaß kontinuierlich sein werden.
  10. Verfahren nach Anspruch 7,
    dadurch gekennzeichnet,
    dass Änderungen in der Prozessorlast nur berücksichtigt werden, wenn sie vordefinierte Grenzen überschreiten.
  11. Verfahren nach Anspruch 1,
    dadurch gekennzeichnet,
    dass der Zustand jedes Prozessors während eines Betriebs überwacht wird, um so Änderungen zu erfassen, die von einem Prozessorverlust verursacht werden; dass sämtliche Verteilungseinheiten, die einem verlorengegangenen Prozessor zugeordnet sind, auf einem oder mehreren der anderen Prozessoren in Übereinstimmung mit dem Redundanzumordnungsschema installiert werden; und dass ein neues Redundanzumordnungsschema berechnet wird.
  12. Verfahren nach Anspruch 11,
    dadurch gekennzeichnet,
    dass die Verteilungseinheiten gleichmäßig unter den Prozessoren in dem Verteilungsschritt verteilt werden.
  13. Verfahren nach Anspruch 11,
    dadurch gekennzeichnet,
    dass die Anzahl von Verteilungseinheiten, die einem Prozessor zugewiesen sind, in dem Verteilungsschritt so gewichtet werden, dass weniger Verteilungseinheiten Prozessoren mit einer stärkeren Last oder mit einer geringeren inhärenten Kapazität zugewiesen werden.
  14. Verfahren nach Anspruch 1,
    dadurch gekennzeichnet,
    dass der anfängliche Verteilungsschritt beinhaltet:
    a) Berechnen eines Schemas einer Verteilung von Verteilungseinheiten über die Prozessoren, wobei Parameter, die die Kapazität jedes Prozessors bestimmen, berücksichtigt werden, so dass die berechnete Verteilung proportional zu Differenzen in der Kapazität der Prozessoren gewichtet wird; und
    b) Verteilen von Gruppen von Verteilungseinheiten über jeweilige Anzahlen von Prozessoren, so dass eine entsprechende Anzahl von Redundanzdomänen in dem System gebildet wird, so dass die Prozessorlast in vernünftiger Weise ausgeglichen wird, in Übereinstimmung mit dem Schema der Verteilung.
  15. Verfahren nach Anspruch 14,
    dadurch gekennzeichnet,
    dass das verteilte Computersystem ein Telekommunikationsvermittlungssystem ist.
  16. Verfahren nach Anspruch 1,
    gekennzeichnet durch
    ein Bestimmen, wie viel Kapazität von jeder Anwendungs-Subfunktion benötigt wird, wobei ein Verlust einer Kapazität z.B. aufgrund eines Prozessorausfalls berücksichtigt wird, und ein Bestimmen, auf wie viel Prozessoren jede Anwendungs-Subfunktion ausgeführt werden wird.
EP95941311A 1994-12-09 1995-12-08 Mechanismus für eine konfigurierung Expired - Lifetime EP0796463B1 (de)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
SE9404295A SE9404295D0 (sv) 1994-12-09 1994-12-09 Sätt och anordning vid telekommunikation
SE9404295 1994-12-09
PCT/SE1995/001484 WO1996018149A2 (en) 1994-12-09 1995-12-08 Configuration mechanism

Publications (2)

Publication Number Publication Date
EP0796463A2 EP0796463A2 (de) 1997-09-24
EP0796463B1 true EP0796463B1 (de) 2001-06-13

Family

ID=20396281

Family Applications (1)

Application Number Title Priority Date Filing Date
EP95941311A Expired - Lifetime EP0796463B1 (de) 1994-12-09 1995-12-08 Mechanismus für eine konfigurierung

Country Status (17)

Country Link
EP (1) EP0796463B1 (de)
JP (1) JPH10511785A (de)
KR (1) KR100331492B1 (de)
CN (1) CN1132097C (de)
AT (1) ATE202225T1 (de)
AU (1) AU716774B2 (de)
BR (1) BR9509895A (de)
CA (1) CA2206373A1 (de)
DE (1) DE69521337T2 (de)
DK (1) DK0796463T3 (de)
ES (1) ES2161918T3 (de)
FI (1) FI972407A0 (de)
GR (1) GR3036045T3 (de)
MX (1) MX9703872A (de)
NO (1) NO972597L (de)
SE (1) SE9404295D0 (de)
WO (1) WO1996018149A2 (de)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2206737C (fr) * 1997-03-27 2000-12-05 Bull S.A. Architecture en reseau de machine informatique
US6038677A (en) * 1997-03-31 2000-03-14 International Business Machines Corporation Automatic resource group formation and maintenance in a high availability cluster configuration
FR2773239A1 (fr) * 1997-12-30 1999-07-02 Bull Sa Configuration d'un systeme informatique multinodal
US20060053424A1 (en) * 2002-06-28 2006-03-09 Tommi Koistinen Load balancing devices and method therefor
WO2004059484A1 (fr) * 2002-12-31 2004-07-15 Zte Corporation Procede de veille et commande de charge dans un systeme a traitement reparti de donnees
US7574708B2 (en) * 2004-03-04 2009-08-11 International Business Machines Corporation Mechanism for enabling the distribution of operating system resources in a multi-node computer system

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5165018A (en) * 1987-01-05 1992-11-17 Motorola, Inc. Self-configuration of nodes in a distributed message-based operating system
US5274838A (en) * 1987-06-03 1993-12-28 Ericsson Ge Mobile Communications Inc. Fail-soft architecture for public trunking system
CA1318409C (en) * 1988-10-27 1993-05-25 Dennis L. Debruler Multiprocessor load sharing arrangement
EP0645702B1 (de) * 1993-09-24 2000-08-02 Siemens Aktiengesellschaft Verfahren zum Lastausgleich in einem Multiprozessorsystem

Also Published As

Publication number Publication date
BR9509895A (pt) 1997-11-25
DE69521337D1 (de) 2001-07-19
WO1996018149A3 (en) 1996-08-15
FI972407A (fi) 1997-06-06
KR980700611A (ko) 1998-03-30
ES2161918T3 (es) 2001-12-16
AU716774B2 (en) 2000-03-09
NO972597L (no) 1997-08-05
SE9404295D0 (sv) 1994-12-09
MX9703872A (es) 1997-08-30
JPH10511785A (ja) 1998-11-10
EP0796463A2 (de) 1997-09-24
ATE202225T1 (de) 2001-06-15
DK0796463T3 (da) 2001-09-03
NO972597D0 (no) 1997-06-06
AU4277196A (en) 1996-06-26
CN1169191A (zh) 1997-12-31
CN1132097C (zh) 2003-12-24
WO1996018149A2 (en) 1996-06-13
KR100331492B1 (ko) 2002-08-22
CA2206373A1 (en) 1996-06-13
DE69521337T2 (de) 2001-10-11
GR3036045T3 (en) 2001-09-28
FI972407A0 (fi) 1997-06-06

Similar Documents

Publication Publication Date Title
US5574914A (en) Method and apparatus for performing system resource partitioning
US5778224A (en) Method of executing a plurality of transactions and a distributed processing system for performing such a method
US5301323A (en) Data processing system including dynamic channel path management
JP4650203B2 (ja) 情報システム及び管理計算機
EP0361974B1 (de) Übertragungssystem für verteilte Datenbanken
US5193171A (en) Method of managing space of peripheral storages and apparatus for the same
JP3478538B2 (ja) 共通ルーチンを用いた移植性の資源共用ファイルサーバ
US7130897B2 (en) Dynamic cluster versioning for a group
US5960178A (en) Queue system and method for point-to-point message passing having a separate table for storing message state and identifier of processor assigned to process the message
CA2104804C (en) Control system of a switching system
KR20050054438A (ko) 복수의 대기 자원의 사용량 관리 방법, 장치 및 프로그램제품
EP0796463B1 (de) Mechanismus für eine konfigurierung
US7568226B2 (en) Data processing system and method
US5974565A (en) Composite computer system
EP0830791A1 (de) Verfügbarkeit von betriebsmitteln in intelligenten telekommunikationsnetzen
CN1181644C (zh) 用于保护数字通信系统的方法
JP2001216174A (ja) アプリケーション代替方法及びアプリケーション代替プログラムを格納した記憶媒体
JP2990650B2 (ja) ネットワーク管理システム
AU699695B2 (en) A computer controlled system
JP7389387B2 (ja) 呼制御装置、呼処理継続方法、および、呼制御プログラム
JPH0345598B2 (de)
JP2953928B2 (ja) 交換機の負荷制御方法とその装置
AU693373C (en) Resource availability in intelligent telecommunications networks
KR100318714B1 (ko) 비동기전송모드교환기에서프로세서간통신스위치포트의동적할당방법
EP0960519B1 (de) Betriebssicheres telekommunikationsnetzwerk mit fernsprechvermittlungsanlagen und datenbanken

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 19970516

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): AT BE CH DE DK ES FR GB GR IE IT LI NL SE

17Q First examination report despatched

Effective date: 20000124

GRAG Despatch of communication of intention to grant

Free format text: ORIGINAL CODE: EPIDOS AGRA

GRAG Despatch of communication of intention to grant

Free format text: ORIGINAL CODE: EPIDOS AGRA

GRAH Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOS IGRA

GRAH Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOS IGRA

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AT BE CH DE DK ES FR GB GR IE IT LI NL SE

REF Corresponds to:

Ref document number: 202225

Country of ref document: AT

Date of ref document: 20010615

Kind code of ref document: T

RIN1 Information on inventor provided before grant (corrected)

Inventor name: LARRUY, RAMON, ALEXANDER

Inventor name: ANDERSSON, SOFIA, BIRGITTA

Inventor name: HOLTE-ROST, ANNA, NAEMI, INGEBORG

REG Reference to a national code

Ref country code: CH

Ref legal event code: NV

Representative=s name: ISLER & PEDRAZZINI AG

REF Corresponds to:

Ref document number: 69521337

Country of ref document: DE

Date of ref document: 20010719

ET Fr: translation filed
REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: DK

Ref legal event code: T3

ITF It: translation for a ep patent filed
PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: NL

Payment date: 20011120

Year of fee payment: 7

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DK

Payment date: 20011121

Year of fee payment: 7

Ref country code: CH

Payment date: 20011121

Year of fee payment: 7

Ref country code: AT

Payment date: 20011121

Year of fee payment: 7

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GR

Payment date: 20011129

Year of fee payment: 7

REG Reference to a national code

Ref country code: ES

Ref legal event code: FG2A

Ref document number: 2161918

Country of ref document: ES

Kind code of ref document: T3

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: IE

Payment date: 20011217

Year of fee payment: 7

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: BE

Payment date: 20011221

Year of fee payment: 7

REG Reference to a national code

Ref country code: GB

Ref legal event code: IF02

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: ES

Payment date: 20020109

Year of fee payment: 7

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

26N No opposition filed
PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: AT

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20021208

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20021209

Ref country code: ES

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20021209

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LI

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20021231

Ref country code: CH

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20021231

Ref country code: BE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20021231

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DK

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20030131

BERE Be: lapsed

Owner name: TELEFONAKTIEBOLAGET L M *ERICSSON (PUBL)

Effective date: 20021231

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: NL

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20030701

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GR

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20030707

REG Reference to a national code

Ref country code: DK

Ref legal event code: EBP

REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

NLV4 Nl: lapsed or anulled due to non-payment of the annual fee

Effective date: 20030701

REG Reference to a national code

Ref country code: IE

Ref legal event code: MM4A

REG Reference to a national code

Ref country code: ES

Ref legal event code: FD2A

Effective date: 20021209

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: SE

Payment date: 20041221

Year of fee payment: 10

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20051209

EUG Se: european patent has lapsed
PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: IT

Payment date: 20071228

Year of fee payment: 13

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20121227

Year of fee payment: 18

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 20130110

Year of fee payment: 18

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 20121231

Year of fee payment: 18

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IT

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20081208

REG Reference to a national code

Ref country code: DE

Ref legal event code: R119

Ref document number: 69521337

Country of ref document: DE

GBPC Gb: european patent ceased through non-payment of renewal fee

Effective date: 20131208

REG Reference to a national code

Ref country code: FR

Ref legal event code: ST

Effective date: 20140829

REG Reference to a national code

Ref country code: DE

Ref legal event code: R119

Ref document number: 69521337

Country of ref document: DE

Effective date: 20140701

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20140701

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: FR

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20131231

Ref country code: GB

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20131208